公开(公告)号：US11983903B2

公开(公告)日：2024-05-14

申请号：US18500034

申请日：2023-11-01

Applicant: Google LLC

Inventor： Neil Matthew Tinmouth Houlsby ,  Sylvain Gelly ,  Jakob D. Uszkoreit ,  Xiaohua Zhai ,  Georg Heigold ,  Lucas Klaus Beyer ,  Alexander Kolesnikov ,  Matthias Johannes Lorenz Minderer ,  Dirk Weissenborn ,  Mostafa Dehghani ,  Alexey Dosovitskiy ,  Thomas Unterthiner

IPC: G06T7/00 ,  G06F18/24 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06T7/97 ,  G06F18/24 ,  G06N3/045 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using self-attention based neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more self-attention neural network layers.

公开(公告)号：US20240038245A1

公开(公告)日：2024-02-01

申请号：US18485069

申请日：2023-10-11

Applicant: Google LLC

Inventor： Georg Heigold ,  Samuel Bengio ,  Ignacio Lopez Moreno

IPC: G10L17/18 ,  G10L17/04 ,  G10L17/02

CPC classification number: G10L17/18 ,  G10L17/04 ,  G10L17/02

Abstract: This document generally describes systems, methods, devices, and other techniques related to speaker verification, including (i) training a neural network for a speaker verification model, (ii) enrolling users at a client device, and (iii) verifying identities of users based on characteristics of the users' voices. Some implementations include a computer-implemented method. The method can include receiving, at a computing device, data that characterizes an utterance of a user of the computing device. A speaker representation can be generated, at the computing device, for the utterance using a neural network on the computing device. The neural network can be trained based on a plurality of training samples that each: (i) include data that characterizes a first utterance and data that characterizes one or more second utterances, and (ii) are labeled as a matching speakers sample or a non-matching speakers sample.

公开(公告)号：US11557277B2

公开(公告)日：2023-01-17

申请号：US17644362

申请日：2021-12-15

Applicant: Google LLC

Inventor： Georg Heigold ,  Erik McDermott ,  Vincent O. VanHoucke ,  Andrew W. Senior ,  Michiel A. U. Bacchiani

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

公开(公告)号：US09978374B2

公开(公告)日：2018-05-22

申请号：US14846187

申请日：2015-09-04

Applicant: Google LLC

Inventor： Georg Heigold ,  Samy Bengio ,  Ignacio Lopez Moreno

IPC: G10L17/18 ,  G10L17/04 ,  G10L17/02

CPC classification number: G10L17/18 ,  G10L17/02 ,  G10L17/04

Abstract: This document generally describes systems, methods, devices, and other techniques related to speaker verification, including (i) training a neural network for a speaker verification model, (ii) enrolling users at a client device, and (iii) verifying identities of users based on characteristics of the users' voices. Some implementations include a computer-implemented method. The method can include receiving, at a computing device, data that characterizes an utterance of a user of the computing device. A speaker representation can be generated, at the computing device, for the utterance using a neural network on the computing device. The neural network can be trained based on a plurality of training samples that each: (i) include data that characterizes a first utterance and data that characterizes one or more second utterances, and (ii) are labeled as a matching speakers sample or a non-matching speakers sample.

公开(公告)号：US11961525B2

公开(公告)日：2024-04-16

申请号：US17444384

申请日：2021-08-03

Applicant: Google LLC

Inventor： Georg Heigold ,  Samuel Bengio ,  Ignacio Lopez Moreno

IPC: G10L17/18 ,  G10L17/02 ,  G10L17/04

CPC classification number: G10L17/18 ,  G10L17/02 ,  G10L17/04

Abstract: This document generally describes systems, methods, devices, and other techniques related to speaker verification, including (i) training a neural network for a speaker verification model, (ii) enrolling users at a client device, and (iii) verifying identities of users based on characteristics of the users' voices. Some implementations include a computer-implemented method. The method can include receiving, at a computing device, data that characterizes an utterance of a user of the computing device. A speaker representation can be generated, at the computing device, for the utterance using a neural network on the computing device. The neural network can be trained based on a plurality of training samples that each: (i) include data that characterizes a first utterance and data that characterizes one or more second utterances, and (ii) are labeled as a matching speakers sample or a non-matching speakers sample.

公开(公告)号：US20220108478A1

公开(公告)日：2022-04-07

申请号：US17492537

申请日：2021-10-01

Applicant: Google LLC

Inventor： Neil Matthew Tinmouth Houlsby ,  Sylvain Gelly ,  Jakob D. Uszkoreit ,  Xiaohua Zhai ,  Georg Heigold ,  Lucas Klaus Beyer ,  Alexander Kolesnikov ,  Matthias Johannes Lorenz Minderer ,  Dirk Weissenborn ,  Mostafa Dehghani ,  Alexey Dosovitskiy ,  Thomas Unterthiner

IPC: G06T7/00 ,  G06N3/04 ,  G06K9/62 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using self-attention based neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more self-attention neural network layers.

公开(公告)号：US20210125601A1

公开(公告)日：2021-04-29

申请号：US17143140

申请日：2021-01-06

Applicant: Google LLC

Inventor： Georg Heigold ,  Erik Mcdermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A.U. Bacchiani

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

公开(公告)号：US20200118549A1

公开(公告)日：2020-04-16

申请号：US16573323

申请日：2019-09-17

Applicant: Google LLC

Inventor： Georg Heigold ,  Erik McDermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A.U. Bacchiani

IPC: G10L15/06 ,  G06N3/04 ,  G10L15/183 ,  G10L15/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

公开(公告)号：US10482873B2

公开(公告)日：2019-11-19

申请号：US15910720

申请日：2018-03-02

Applicant: Google LLC

Inventor： Georg Heigold ,  Erik McDermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A. U. Bacchiani

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

公开(公告)号：US12125247B2

公开(公告)日：2024-10-22

申请号：US17492537

申请日：2021-10-01

Applicant: Google LLC

Inventor： Neil Matthew Tinmouth Houlsby ,  Sylvain Gelly ,  Jakob D. Uszkoreit ,  Xiaohua Zhai ,  Georg Heigold ,  Lucas Klaus Beyer ,  Alexander Kolesnikov ,  Matthias Johannes Lorenz Minderer ,  Dirk Weissenborn ,  Mostafa Dehghani ,  Alexey Dosovitskiy ,  Thomas Unterthiner

IPC: G06T7/00 ,  G06F18/24 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06T7/97 ,  G06F18/24 ,  G06N3/045 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using self-attention based neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more self-attention neural network layers.